Yangyang Wu

Dr. Yangyang Wu


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2019 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
YWYangyang Wu
Yangyang Wu
LFLu Fan
Lu Fan
XLXiang Lin
Xiang Lin
HZHaibin Zheng
Haibin Zheng
QXQi Xuan
Qi Xuan
Recommender systems are becoming more and more important in our daily lives. However, traditional recommendation methods are challenged by data sparsity and efficiency, as the numbers of users, items, and interactions between the two in many real-world applications increase fast. In this paper, we propose a novel clustering recommender system based on node2vec technology and rich information network, namely, N2VSCDNNR, to solve these challenges. In particular, we use a bipartite network to construct the user–item network and represent the interactions among users (or items) by the corresponding one-mode projection network. In order to alleviate the data sparsity problem, we enrich the network structure according to user and item categories, and construct the one-mode projection category network. Then, considering the data sparsity problem in the network, we employ node2vec to capture the complex latent relationships among users (or items) from the corresponding one-mode projection category network. Moreover, considering the dependence on parameter settings and information loss problem in clustering methods, we use a novel spectral clustering method, which is based on dynamic nearest-neighbors (DNNs) and a novel automatically determining cluster number (ADCN) method that determines the cluster centers based on the normal distribution method, to cluster the users and items separately. After clustering, we propose the two-phase personalized recommendation to realize the personalized recommendation of items for each user. A series of experiments validate the outstanding performance of our N2VSCDNNR over several advanced embedding and side information based recommendation algorithms. Meanwhile, N2VSCDNNR seems to have lower time complexity than the baseline methods in online recommendations, indicating its potential to be widely applied in large-scale systems.

23 December 2020 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
XLXiang Lin
Xiang Lin
HXHui Xiong
Hui Xiong
YWYangyang Wu
Yangyang Wu
HZHaibin Zheng
Haibin Zheng
QXQi Xuan
Qi Xuan
Recently, a graph neural network (GNN) was proposed to analyze various graphs/networks, which has been proven to outperform many other network analysis methods. However, it is also shown that such state-of-the-art methods suffer from adversarial attacks, i.e., carefully crafted adversarial networks with slight perturbation on clean one may invalid these methods on lots of applications, such as network embedding, node classification, link prediction, and community detection. Adversarial training has been testified as an efficient defense strategy against adversarial attacks in computer vision and graph mining. However, almost all the algorithms based on adversarial training focus on global defense through overall adversarial training. In a more practical scene, certain users would be targeted to attack, i.e., specific labeled users. It is still a challenge to defend against target node attack by existing adversarial training methods. Therefore, we propose smoothing adversarial training (SAT) to improve the robustness of GNNs. In particular, we analytically investigate the robustness of graph convolutional network (GCN), one of the classic GNNs, and propose two smooth defensive strategies: smoothing distillation and smoothing cross-entropy loss function. Both of them smooth the gradients of GCN and, consequently, reduce the amplitude of adversarial gradients, benefiting gradient masking from attackers in both global attack and target label node attack. The comprehensive experiments on five real-world networks testify that the proposed SAT method shows state-of-the-art defensibility against different adversarial attacks on node classification and community detection. Especially, the average attack success rate of different attack methods can be decreased by about 40% by SAT at the cost of tolerable embedding performance decline of the original network.

7 July 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YWYangyang Wu
Yangyang Wu
JWJun Wang
Jun Wang
XMXiaoye Miao
Xiaoye Miao
WWWenjia Wang
Wenjia Wang
JYJianwei Yin
Jianwei Yin
Data imputation has been extensively explored to solve the missing data problem. The dramatically increasing volume of incomplete data makes the imputation models computationally infeasible in many real-life applications. In this paper, we propose an effective scalable imputation system named SCIS to significantly speed up the training of the differentiable generative adversarial imputation models under accuracy-guarantees for large-scale incomplete data. SCIS consists of two modules, differentiable imputation modeling (DIM) and sample size estimation (SSE). DIM leverages a new masking Sinkhorn divergence function to make an arbitrary generative adversarial imputation model differentiable, while for such a differentiable imputation model, SSE can estimate an appropriate sample size to ensure the user-specified imputation accuracy of the final model. Moreover, SCIS can also accelerate the autoencoder based imputation models. Extensive experiments upon several real-life large-scale datasets demonstrate that, our proposed system can accelerate the generative adversarial model training by 6.23x. Using around 1.27% samples, SCIS yields competitive accuracy with the state-of-the-art imputation methods in much shorter computation time.

5 July 2024
Verified
Conference Paper
Open access
WNWei Ni
Wei Ni
KZKaihang Zhang
Kaihang Zhang
XMXiaoye Miao
Xiaoye Miao
XZXiangyu Zhao
Xiangyu Zhao
YWYangyang Wu
Yangyang Wu
JYJianwei Yin
Jianwei Yin
In the era of generative artificial intelligence, the accuracy of data is paramount. Erroneous data often leads to faulty outcomes and economic detriments. Previous cleaning methods employ a sequential detect-repair paradigm, leaving over half of the errors unsolved in real scenarios. We introduce IterClean, an iterative data cleaning framework leveraging large language models (LLMs). Utilizing an iterative mechanism, the framework employs a two-step process: data labeling and iterative data cleaning. With few labeled data, IterClean leverages an iterative cleaning process involving an error detector, an error verifier, and an error repairer to significantly enhance the cleaning performance. Extensive experiments across four datasets demonstrate that, IterClean achieves an F1 score that is up to three times higher than the best state-of-the-art approaches requiring only 5 labeled tuples.

21 June 2024 in IEEE Transactions on Services Computing
Verified
Journal Article
Closed access
XWXuanye Wang
Xuanye Wang
MXMeng Xi
Meng Xi
YLYing Li
Ying Li
XPXiaohua Pan
Xiaohua Pan
YWYangyang Wu
Yangyang Wu
JYJianwei Yin
Jianwei Yin
With the growth of cloud computing, a large number of innovative mashup applications and Web APIs have emerged on the Internet. The expansion of technology and information presents a significant challenge to the discovery of Web APIs from multiple service ecosystems. Various Web API recommendation methods have been proposed for Mashup creation, but most either treat different feature factor interactions equally or solely rely on requirements for API recommendation. These approaches face several challenges such as API compatibility dependencies, ambiguous definition and boundary dilemmas of APIs, and sparse API invocation records. In this work, we propose a Semantic-Enhanced Heterogeneous Graph Network(SEHGN) for Mashup creation. To address the above deficiencies, we design a multi-semantic aggregator to capture semantic associations between features to encode multiple node-edge relationships. Then, we introduce a semantic embedding component to generate text embedding vectors for mashups and APIs to learn global and local semantic information about text documents at different levels of abstraction. Finally, we fuse the output vectors to obtain a list of candidate Web APIs. Experiences are performed on real datasets, and statistical results show that SEHGN outperforms state-of-the-art models in terms of overall and long-tail Web API recommendations.

23 May 2019 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
JCJinyin Chen
Jinyin Chen
YWYangyang Wu
Yangyang Wu
XXXuanheng Xu
Xuanheng Xu
HZHaibin Zheng
Haibin Zheng
ZRZhongyuan Ruan
Zhongyuan Ruan
QXQi Xuan
Qi Xuan
Network embedding plays an important role in various network applications, such as node classification and link prediction. Lots of structure-based network embedding methods have been proposed. Yet, they suffer from unsteady embedding performances due to the parameter sensitivity. How to extract valuable attribute information in networks with less parameter influence is still a challenge. In this paper, we propose a novel algorithm, named adaptive network embedding with particle swarm optimization (PSO-ANE), which is based on the second-order dynamic random walk and PSO method, for learning network representations. A second-order dynamic random walk is designed to search a suitable strategy for each node based on the structure-based transition probability, the centrality-based transition probability, and the static link weights. To reduce the parameter dependence, PSO is adopted for key-parameter optimization to get global steady network embedding. The experiments validate that the proposed method outperforms the existing state-of-the-art techniques on multilabel classification, multiclass classification, and link prediction tasks.